Efficient evaluation of photodynamic therapy on tumor based on deep learning.
Photodiagnosis Photodyn Ther
; 43: 103658, 2023 Sep.
Article
em En
| MEDLINE
| ID: mdl-37339692
ABSTRACT
Photodynamic therapy (PDT) is a non-invasive treatment method for treating tumors. Under laser irradiation, photosensitizers in tumor tissues generate biotoxic reactive oxygen, which can kill tumor cells. The traditional live/dead staining method of evaluating the cell mortality caused by PDT mainly depends on manual counting, which is time-consuming and relies on dye quality. In this paper, we have constructed a dataset of cells after PDT treatment and trained the cell detection model YOLOv3 to count both the dead and live cells. YOLO is a real time AI object detection algorithm. The achieved results demonstrate that the proposed method has a good performance in cell detection, with a mean average precision (mAP) of 94% for live cells and 71.3% for dead cells. This approach can efficiently evaluate the effectiveness of PDT treatment, thus speeding up treatment development effectively.
Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Fotoquimioterapia
/
Aprendizado Profundo
/
Neoplasias
Tipo de estudo:
Guideline
Limite:
Humans
Idioma:
En
Revista:
Photodiagnosis Photodyn Ther
Assunto da revista:
DIAGNOSTICO POR IMAGEM
/
TERAPEUTICA
Ano de publicação:
2023
Tipo de documento:
Article
País de afiliação:
China